{"ID":2834115,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.02965","arxiv_id":"2512.02965","title":"A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems","abstract":"In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose UltraFast-LieNET, a lightweight multi-scale shifted convolutional network for real-time low-light image enhancement. We introduce a Dynamic Shifted Convolution (DSConv) kernel with only 12 learnable parameters for efficient feature extraction. By integrating DSConv with varying shift distances, a Multi-scale Shifted Residual Block (MSRB) is constructed to significantly expand the receptive field. To mitigate lightweight network instability, a residual structure and a novel multi-level gradient-aware loss function are incorporated. UltraFast-LieNET allows flexible parameter configuration, with a minimum size of only 36 parameters. Results on the LOLI-Street dataset show a PSNR of 26.51 dB, outperforming state-of-the-art methods by 4.6 dB while utilizing only 180 parameters. Experiments across four benchmark datasets validate its superior balance of real-time performance and enhancement quality under limited resources. Code is available at https://githubhttps://github.com/YuhanChen2024/UltraFast-LiNET","short_abstract":"In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose UltraFast-LieNET, a lightweight multi-scale shifted convolutional network for real-time l...","url_abs":"https://arxiv.org/abs/2512.02965","url_pdf":"https://arxiv.org/pdf/2512.02965v1","authors":"[\"Yuhan Chen\",\"Yicui Shi\",\"Guofa Li\",\"Guangrui Bai\",\"Jinyuan Shao\",\"Xiangfei Huang\",\"Wenbo Chu\",\"Keqiang Li\"]","published":"2025-12-02T17:44:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","project_urls":"[\"https://githubhttps://github.com/YuhanChen2024/UltraFast-LiNET\"]","has_code":false,"code_links":[{"ID":606384,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2834115,"paper_url":"https://arxiv.org/abs/2512.02965","paper_title":"A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems","repo_url":"https://github.com/YuhanChen2024/UltraFast-LiNET","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}